Printing Press Amend

You just dogfooded a CLI from the printing press library, hit friction, and hand-rolled a workaround in the session. This skill mines that transcript for missing flags, wonky API payloads, or silent nulls, confirms scope with you, then autonomously plans and executes the fix before opening a PR against the public library. It also handles direct-input mode when you already know what you want: rename a command, add feeds, sniff the source site for new endpoints. Two checkpoints keep you in the loop without making you write the patch yourself. The currency floor check stops it from regenerating CLIs with known bugs if your local binary is stale. It's the post-publish companion to the polish and publish skills.

skills.sh installs: 5.7K
GitHub stars: 4.9K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add mvanhorn/cli-printing-press --skill printing-press-amend --agent claude-code

Installs into .claude/skills of the current project.

Files

/printing-press-amend

Turn a dogfood session into a PR for a printed CLI in the public library.

/printing-press-amend                 # auto-detect target CLI from session
/printing-press-amend superhuman      # explicit short name
/printing-press-amend superhuman-pp-cli
/printing-press-amend "$PRESS_LIBRARY/superhuman"

This skill lives in this repo (the machine) and acts on a printed CLI in the public library. It is sibling to /printing-press-publish (adds a new CLI), /printing-press-polish (improves a CLI pre-publish), and /printing-press-retro (reflects on the machine itself). None of those cover post-publish CLI amendments driven by real-session friction.

The artifact this skill produces is semantically a "patch" (in the git/PR sense), tracked by the public library's .printing-press-patches/ directory (one file per patch). Inline // PATCH(...) source comments are optional navigation aids when they make a customized site easier to grep. The slash-skill name is amend to disambiguate from the existing cli-printing-press patch binary subcommand (which AST-injects pre-defined features — different mechanism, different intent).